nerdyrodent/VQGAN-CLIP

Just playing with getting VQGAN+CLIP running locally, rather than having to use colab.

49
/ 100
Emerging

This project helps artists, designers, and creative enthusiasts generate unique images from text descriptions or existing images. You input a text prompt describing what you want to see (e.g., "A painting of an apple in a fruit bowl") and optionally an image to influence the style, and the system outputs a new, original image matching your description. It's for anyone looking to quickly visualize concepts or create digital art without needing traditional drawing skills.

2,653 stars. No commits in the last 6 months.

Use this if you want to create original digital art or conceptual images by simply describing them in text, or if you want to apply a specific artistic style to an existing image.

Not ideal if you need fine-grained control over every pixel, precise photo editing, or if you don't have access to a powerful computer with a dedicated graphics card.

digital-art concept-generation graphic-design creative-imaging visual-prototyping
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 23 / 25

How are scores calculated?

Stars

2,653

Forks

426

Language

Python

License

Last pushed

Oct 02, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/nerdyrodent/VQGAN-CLIP"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.